feat(ingestion): supporto multi-documento in unica collection ChromaDB

Aggiunge la possibilità di unire più documenti in una singola collection
ChromaDB, con chunk_id prefissati per stem e metadato source per filtrare.

- ingest.py: --stems doc1 doc2 --collection nome (nuovo), --stem (invariato)
- rag.py / retrieve.py: --collection, source nei chunk, verbose mostra [source]

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

rag.py

@@ -101,6 +101,7 @@ def retrieve(collection: chromadb.Collection, question: str) -> list[dict]:
     ):
         chunks.append({
             "text":     text,
+            "source":   meta.get("source", ""),
             "sezione":  meta.get("sezione", ""),
             "titolo":   meta.get("titolo", ""),
             "distance": dist,
@@ -143,7 +144,8 @@ def answer(question: str, collection: chromadb.Collection, verbose: bool) -> Non
             if c["titolo"]:
                 loc += f" > {c['titolo']}"
             sim = 1 - c["distance"]
-            print(f"  [{i}] {loc}  (similarità: {sim:.3f})")
+            src = f"[{c['source']}] " if c.get("source") else ""
+            print(f"  [{i}] {src}{loc}  (similarità: {sim:.3f})")
             print(f"      {c['text'][:120].replace(chr(10), ' ')}...")
         print("──────────────────────────────────────────────────────────────\n")
 
@@ -215,19 +217,23 @@ def main() -> int:
     )
     parser.add_argument(
         "--stem",
-        required=True,
-        help=(
-            "Nome della collection ChromaDB da interrogare. "
-            "Le collection vengono create da: python ingestion/ingest.py --stem <nome>"
-        ),
+        help="Collection di un singolo documento (retrocompatibile)",
+    )
+    parser.add_argument(
+        "--collection",
+        help="Collection multi-documento creata con: ingest.py --collection <nome> --stems ...",
     )
     args = parser.parse_args()
 
+    collection_name = args.collection or args.stem
+    if not collection_name:
+        parser.error("specifica --stem <nome> oppure --collection <nome>")
+
     print("─── Pipeline RAG ────────────────────────────────────────────\n")
-    print(f"  Documento : {args.stem}")
-    print(f"  Modello   : {LLM_MODEL}")
-    print(f"  Top-K     : {TOP_K}")
-    print(f"  Thinking  : {'off' if NO_THINK else 'on'}")
+    print(f"  Collection : {collection_name}")
+    print(f"  Modello    : {LLM_MODEL}")
+    print(f"  Top-K      : {TOP_K}")
+    print(f"  Thinking   : {'off' if NO_THINK else 'on'}")
     print()
 
     if not CHROMA_DIR.exists():
@@ -236,13 +242,16 @@ def main() -> int:
 
     client = chromadb.PersistentClient(path=str(CHROMA_DIR))
     collections = [c.name for c in client.list_collections()]
-    if args.stem not in collections:
-        print(f"❌ Collection '{args.stem}' non trovata in chroma_db/")
-        print(f"   → python ingestion/ingest.py --stem {args.stem}")
+    if collection_name not in collections:
+        print(f"❌ Collection '{collection_name}' non trovata in chroma_db/")
+        if args.stem:
+            print(f"   → python ingestion/ingest.py --stem {collection_name}")
+        else:
+            print(f"   → python ingestion/ingest.py --collection {collection_name} --stems doc1 doc2 ...")
         return 1
 
-    collection = client.get_collection(args.stem)
-    print(f"✅ Collection '{args.stem}' caricata ({collection.count()} chunk)\n")
+    collection = client.get_collection(collection_name)
+    print(f"✅ Collection '{collection_name}' caricata ({collection.count()} chunk)\n")
 
     run_loop(collection)
     return 0